This paper presents a system of sensors used in flash flood prediction that offers critical real-time information used to provide early warnings that can provide the minutes needed for persons to evacuate before imminent events. Flooding is one of the most serious natural disasters humans confront in terms of loss of life and results in long-term effects, which often have severely adverse social consequences. However, flash floods are potentially more dangerous to life because there is often little or no forewarning of the impending disaster. The Emergency Water Information Network (EWIN) offers a solution that integrates an early warning system, notifications, and real-time monitoring of flash flood risks. The platform has been implemented in Colima, Mexico covering the Colima and Villa de Alvarez metropolitan area. This platform consists of eight fixed riverside hydrological monitoring stations, eight meteorological stations, nomadic mobile monitoring stations called “drifters” used in the flow, and a sniffer with data muling capability. The results show that this platform effectively compiles and forwards information to decision-makers, government officials, and the general public, potentially providing valuable minutes for people to evacuate dangerous areas.

Floods are the most common phenomenon and cause the most significant economic and social damage to the population. They are becoming more frequent and dangerous. Consequently, it is necessary to create strategies to intervene effectively in the mitigation and resilience of the affected areas. Different methods and techniques have been developed to mitigate the damage caused by this phenomenon. Satellite programs provide a large amount of data on the earth's surface, and geospatial information processing tools help manage different natural disasters. Likewise, deep learning is an approach capable of forecasting time series that can be applied to satellite images for flood prediction and mapping. This article presents an approach for flood segmentation and visualization using the U-Net architecture and Sentinel-1 synthetic aperture radar (SAR) satellite imagery. The U-Net architecture can capture relevant features in SAR images. The approach comprises various phases, from data loading and preprocessing to flood inference and visualization. For the study, the georeferenced dataset Sen1Floods11 is used to train and validate the model through different epochs and training. A study area in southeastern Mexico that presents frequent floods was chosen. The results demonstrate that the segmentation model achieves high accuracy in detecting flooded areas, with promising metrics regarding loss, precision, and F1-score.